© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34447
    Prev
    Next
    INDEX
    Explanations

    position and dimension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clientWidth
    -1.06
     adatto
    -1.03
     потім
    -1.01
    blica
    -0.99
     Collapse
    -0.98
     MatDialog
    -0.98
    pylene
    -0.95
    adari
    -0.94
     viena
    -0.94
     démission
    -0.93
    POSITIVE LOGITS
    かれています
    1.00
     II
    0.92
     от
    0.87
    相手の
    0.85
     was
    0.85
    0.85
    ,
    0.85
     RED
    0.82
    contentValues
    0.81
     artículo
    0.81
    Activations Density 0.007%

    No Known Activations